Class Geometry as Supervision for Sample-Efficient Open-World Detection

2026-08-12

AI Summary

This work addresses the challenges of few-shot known-class detection, unknown-class rejection, and continual learning of novel classes in open-world object detection. To this end, the authors propose a Category Geometry Supervision (CGS) framework, which, for the first time, leverages the geometric structure of inter-class relationships as a supervisory signal in detection models. By introducing a category geometry alignment loss in the prototype representation space, CGS preserves the visual-semantic dissimilarity structure among categories estimated from training data. Integrated within a prototype-based detection architecture alongside standard task losses, the method substantially improves performance across few-shot detection, open-set recognition, and incremental novel-class learning scenarios. Experiments on benchmarks such as COCO demonstrate consistent gains in few-shot detection accuracy, novel-class incorporation, and unknown-class recall, without compromising known-class detection performance.

Abstract

Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time. This is especially challenging in scarce-data settings such as biomedical and scientific imaging, where rare categories may have only a few annotated examples and fine-grained classes differ by subtle morphology. Prototype-based detectors are natural for this regime, but they typically learn class prototypes as independent anchors, ignoring relational structure among classes. We propose class-geometry supervision (CGS), a general framework that constrains learned prototype or class-representation spaces to preserve visual or semantic class dissimilarities estimated from training data. CGS introduces a dissimilarity-preserving objective that aligns pairwise distances among learned class representations with a target class-geometry matrix while retaining the standard task loss. We instantiate the same objective across prototype recognition, few-shot biomedical object detection, open-set detection, novel-class insertion, and OWOD adaptation on COCO. Experiments show that CGS improves sample efficiency in recognition and ova detection, substantially strengthens novel-class insertion, and improves unknown recall on COCO while retaining much of the known-class detection performance. Ablations show that meaningful visual geometry provides the most reliable gains, while random geometry can help novel separation but is less consistent for few-shot detection. These results suggest that relational class geometry is an effective supervisory signal for building calibrated and extensible open-world detectors under limited supervision.

Problem

• open-world detection
• sample efficiency
• class geometry
• few-shot learning
• novel-class insertion

Innovation

• class-geometry supervision
• prototype-based detection
• open-world object detection
• few-shot learning
• relational class structure